Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving

In this study, we propose an enhanced LiDAR-based mapping and localization system that utilizes a camera-based YOLO (You Only Look Once) algorithm to detect and remove dynamic objects, such as vehicles, from the mapping process. GPS, while commonly used for localization, often fails in urban environ...

Full description

Saved in:
Bibliographic Details
Main Authors: Seonghark Jeong, Heeseok Shin, Myeong-Jun Kim, Dongwan Kang, Seangwock Lee, Sangki Oh
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850107115739283456
author Seonghark Jeong
Heeseok Shin
Myeong-Jun Kim
Dongwan Kang
Seangwock Lee
Sangki Oh
author_facet Seonghark Jeong
Heeseok Shin
Myeong-Jun Kim
Dongwan Kang
Seangwock Lee
Sangki Oh
author_sort Seonghark Jeong
collection DOAJ
description In this study, we propose an enhanced LiDAR-based mapping and localization system that utilizes a camera-based YOLO (You Only Look Once) algorithm to detect and remove dynamic objects, such as vehicles, from the mapping process. GPS, while commonly used for localization, often fails in urban environments due to signal blockages. To address this limitation, our system integrates YOLOv4 with LiDAR, enabling the removal of dynamic objects to improve map accuracy and localization in high-traffic areas. Existing methods using LiDAR segmentation for map matching often suffer from missed detections and false positives, degrading performance. Our approach leverages YOLOv4’s robust object detection capabilities to eliminate potentially dynamic objects while retaining static environmental features, such as buildings, to enhance map accuracy and reliability. The proposed system was validated using a mid-size SUV equipped with LiDAR and camera sensors. The experimental results demonstrate significant improvements in map-matching and localization performance, particularly in urban environments. The system achieved RMSE (Root Mean Square Error) reductions compared to conventional methods, with RMSE values decreasing from 0.9870 to 0.9724 in open areas and from 1.3874 to 1.1217 in urban areas. These findings highlight the ability of the Vision + LiDAR + NDT method to enhance localization performance in both simple and complex environments. By addressing the challenges of dynamic obstacles, the proposed system effectively improves the accuracy and robustness of autonomous navigation in high-traffic settings without relying on GPS.
format Article
id doaj-art-b97beeda7d7f4e04bd5c4e7453254b32
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b97beeda7d7f4e04bd5c4e7453254b322025-08-20T02:38:39ZengMDPI AGSensors1424-82202024-11-012423757810.3390/s24237578Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous DrivingSeonghark Jeong0Heeseok Shin1Myeong-Jun Kim2Dongwan Kang3Seangwock Lee4Sangki Oh5Propulsion Division, GM Korea Company, Incheon 21344, Republic of KoreaConvergence Major for Intelligent Drone, Sejong University, Seoul 05006, Republic of KoreaGraduate School of Automotive Mobility, Kookmin University, Seoul 02707, Republic of KoreaHanwha Aerospace, Seongnam 13488, Republic of KoreaGraduate School of Automotive Mobility, Kookmin University, Seoul 02707, Republic of KoreaDepartment of Automotive Engineering, Gyeonggi University of Science and Technology, Siheung 15073, Republic of KoreaIn this study, we propose an enhanced LiDAR-based mapping and localization system that utilizes a camera-based YOLO (You Only Look Once) algorithm to detect and remove dynamic objects, such as vehicles, from the mapping process. GPS, while commonly used for localization, often fails in urban environments due to signal blockages. To address this limitation, our system integrates YOLOv4 with LiDAR, enabling the removal of dynamic objects to improve map accuracy and localization in high-traffic areas. Existing methods using LiDAR segmentation for map matching often suffer from missed detections and false positives, degrading performance. Our approach leverages YOLOv4’s robust object detection capabilities to eliminate potentially dynamic objects while retaining static environmental features, such as buildings, to enhance map accuracy and reliability. The proposed system was validated using a mid-size SUV equipped with LiDAR and camera sensors. The experimental results demonstrate significant improvements in map-matching and localization performance, particularly in urban environments. The system achieved RMSE (Root Mean Square Error) reductions compared to conventional methods, with RMSE values decreasing from 0.9870 to 0.9724 in open areas and from 1.3874 to 1.1217 in urban areas. These findings highlight the ability of the Vision + LiDAR + NDT method to enhance localization performance in both simple and complex environments. By addressing the challenges of dynamic obstacles, the proposed system effectively improves the accuracy and robustness of autonomous navigation in high-traffic settings without relying on GPS.https://www.mdpi.com/1424-8220/24/23/7578LiDARNDTautonomous vehiclesemantic segmentationlocalizationmap matching
spellingShingle Seonghark Jeong
Heeseok Shin
Myeong-Jun Kim
Dongwan Kang
Seangwock Lee
Sangki Oh
Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
Sensors
LiDAR
NDT
autonomous vehicle
semantic segmentation
localization
map matching
title Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
title_full Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
title_fullStr Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
title_full_unstemmed Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
title_short Enhancing LiDAR Mapping with YOLO-Based Potential Dynamic Object Removal in Autonomous Driving
title_sort enhancing lidar mapping with yolo based potential dynamic object removal in autonomous driving
topic LiDAR
NDT
autonomous vehicle
semantic segmentation
localization
map matching
url https://www.mdpi.com/1424-8220/24/23/7578
work_keys_str_mv AT seongharkjeong enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving
AT heeseokshin enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving
AT myeongjunkim enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving
AT dongwankang enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving
AT seangwocklee enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving
AT sangkioh enhancinglidarmappingwithyolobasedpotentialdynamicobjectremovalinautonomousdriving